Skip to Main Content
Harris corner detection is a widely used corner detection algorithm, however deficiencies still exist: the detected corners are clustered and anti-interference ability is poor. In this paper, a method based on image compression and block processing is proposed to solve these deficiencies. It reduces the clustering phenomenon, increases the detection accuracy, and improves processing speed greatly. Experimental results confirm the validity of the new method and show that the new method greatly improves image corner detection performance with higher accuracy and real-time property compared with the traditional algorithm.